Multi-hop Question Answering on HotpotQA (EM, F1, Time)
61.4EMG-reasoner
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| G-reasoner2025.09 | 61.4 | 76 | 0.114 | |
| R1-searcher2025.09 | 61.2 | 73.8 | 0.532 | |
| Search-R12025.09 | 60.8 | 74.3 | 0.496 | |
| IRCoT2025.09 | 45.5 | 58.4 | 1.146 |
| Method | Links | |||
|---|---|---|---|---|
| G-reasoner2025.09 | 61.4 | 76 | 0.114 | |
| R1-searcher2025.09 | 61.2 | 73.8 | 0.532 | |
| Search-R12025.09 | 60.8 | 74.3 | 0.496 | |
| IRCoT2025.09 | 45.5 | 58.4 | 1.146 |